Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3352 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0522. Min Range: -9.0522
Max Act: 9.0522. Min Act: -0.1700
Data Index: 7147836 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.9897. Min Act: -0.1700
Data Index: 2687556 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.9272. Min Act: -0.1700
Data Index: 2173208 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.9897. Min Act: -0.1700
Data Index: 7644548 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.9897. Min Act: -0.1700
Data Index: 6840845 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.9897. Min Act: -0.1700
Data Index: 6592072 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.9272. Min Act: -0.1700
Data Index: 8244986 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.9272. Min Act: -0.1700
Data Index: 7476032 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.8022. Min Act: -0.1700
Data Index: 4130505 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.6147. Min Act: -0.1700
Data Index: 5115441 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.6147. Min Act: -0.1700
Data Index: 6476076 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.5210. Min Act: -0.1700
Data Index: 6217733 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.5210. Min Act: -0.1700
Data Index: 1228249 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.4897. Min Act: -0.1700
Data Index: 1014869 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.4585. Min Act: -0.1700
Data Index: 1241539 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.4897. Min Act: -0.1700
Data Index: 3295802 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.4585. Min Act: -0.1700
Data Index: 5068035 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.4585. Min Act: -0.1700
Data Index: 7839931 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.3960. Min Act: -0.1700
Data Index: 6549220 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0522. Min Range: -9.0522
Max Act: 7.4272. Min Act: -0.1700
Data Index: 4854954 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19